arXiv subjects

Biplab Banerjee

Publications and source records attributed to Biplab Banerjee.

At least 73 records · Page 4Linked to original sources

arXiv2023

GOPro: Generate and Optimize Prompts in CLIP using Self-Supervised Learning

Large-scale foundation models, such as CLIP, have demonstrated remarkable success in visual recognition tasks by embedding images in a semantically rich space. Self-supervised learning (SSL) has also shown promise in improving visual recognition by learning invariant features. However, the combination of CLIP with SSL is found to face challenges due to the multi-task framework that blends CLIP's contrastive loss and SSL's loss, including difficulties with loss weighting and inconsistency among different views of images in CLIP's output space. To overcome these challenges, we propose a prompt learning-based model called GOPro, which is a unified framework that ensures similarity between various augmented views of input images in a shared image-text embedding space, using a pair of learnable image and text projectors atop CLIP, to promote invariance and generalizability. To automatically learn such prompts, we leverage the visual content and style primitives extracted from pre-trained CLIP and adapt them to the target task. In addition to CLIP's cross-domain contrastive loss, we introduce a visual contrastive loss and a novel prompt consistency loss, considering the different views of the images. GOPro is trained end-to-end on all three loss objectives, combining the strengths of CLIP and SSL in a principled manner. Empirical evaluations demonstrate that GOPro outperforms the state-of-the-art prompting techniques on three challenging domain generalization tasks across multiple benchmarks by a significant margin. Our code is available at https://github.com/mainaksingha01/GOPro.

cs.CV↗

arXiv2023

Temporal DINO: A Self-supervised Video Strategy to Enhance Action Prediction

The emerging field of action prediction plays a vital role in various computer vision applications such as autonomous driving, activity analysis and human-computer interaction. Despite significant advancements, accurately predicting future actions remains a challenging problem due to high dimensionality, complex dynamics and uncertainties inherent in video data. Traditional supervised approaches require large amounts of labelled data, which is expensive and time-consuming to obtain. This paper introduces a novel self-supervised video strategy for enhancing action prediction inspired by DINO (self-distillation with no labels). The Temporal-DINO approach employs two models; a 'student' processing past frames; and a 'teacher' processing both past and future frames, enabling a broader temporal context. During training, the teacher guides the student to learn future context by only observing past frames. The strategy is evaluated on ROAD dataset for the action prediction downstream task using 3D-ResNet, Transformer, and LSTM architectures. The experimental results showcase significant improvements in prediction performance across these architectures, with our method achieving an average enhancement of 9.9% Precision Points (PP), highlighting its effectiveness in enhancing the backbones' capabilities of capturing long-term dependencies. Furthermore, our approach demonstrates efficiency regarding the pretraining dataset size and the number of epochs required. This method overcomes limitations present in other approaches, including considering various backbone architectures, addressing multiple prediction horizons, reducing reliance on hand-crafted augmentations, and streamlining the pretraining process into a single stage. These findings highlight the potential of our approach in diverse video-based tasks such as activity recognition, motion planning, and scene understanding.

cs.CV↗

arXiv2023

Physically Plausible 3D Human-Scene Reconstruction from Monocular RGB Image using an Adversarial Learning Approach

Holistic 3D human-scene reconstruction is a crucial and emerging research area in robot perception. A key challenge in holistic 3D human-scene reconstruction is to generate a physically plausible 3D scene from a single monocular RGB image. The existing research mainly proposes optimization-based approaches for reconstructing the scene from a sequence of RGB frames with explicitly defined physical laws and constraints between different scene elements (humans and objects). However, it is hard to explicitly define and model every physical law in every scenario. This paper proposes using an implicit feature representation of the scene elements to distinguish a physically plausible alignment of humans and objects from an implausible one. We propose using a graph-based holistic representation with an encoded physical representation of the scene to analyze the human-object and object-object interactions within the scene. Using this graphical representation, we adversarially train our model to learn the feasible alignments of the scene elements from the training data itself without explicitly defining the laws and constraints between them. Unlike the existing inference-time optimization-based approaches, we use this adversarially trained model to produce a per-frame 3D reconstruction of the scene that abides by the physical laws and constraints. Our learning-based method achieves comparable 3D reconstruction quality to existing optimization-based holistic human-scene reconstruction methods and does not need inference time optimization. This makes it better suited when compared to existing methods, for potential use in robotic applications, such as robot navigation, etc.

cs.CV↗

arXiv2023

Visual Question Answering in Remote Sensing with Cross-Attention and Multimodal Information Bottleneck

In this research, we deal with the problem of visual question answering (VQA) in remote sensing. While remotely sensed images contain information significant for the task of identification and object detection, they pose a great challenge in their processing because of high dimensionality, volume and redundancy. Furthermore, processing image information jointly with language features adds additional constraints, such as mapping the corresponding image and language features. To handle this problem, we propose a cross attention based approach combined with information maximization. The CNN-LSTM based cross-attention highlights the information in the image and language modalities and establishes a connection between the two, while information maximization learns a low dimensional bottleneck layer, that has all the relevant information required to carry out the VQA task. We evaluate our method on two VQA remote sensing datasets of different resolutions. For the high resolution dataset, we achieve an overall accuracy of 79.11% and 73.87% for the two test sets while for the low resolution dataset, we achieve an overall accuracy of 85.98%.

cs.CV↗

arXiv2023

Semi-Supervised Learning for hyperspectral images by non parametrically predicting view assignment

Hyperspectral image (HSI) classification is gaining a lot of momentum in present time because of high inherent spectral information within the images. However, these images suffer from the problem of curse of dimensionality and usually require a large number samples for tasks such as classification, especially in supervised setting. Recently, to effectively train the deep learning models with minimal labelled samples, the unlabeled samples are also being leveraged in self-supervised and semi-supervised setting. In this work, we leverage the idea of semi-supervised learning to assist the discriminative self-supervised pretraining of the models. The proposed method takes different augmented views of the unlabeled samples as input and assigns them the same pseudo-label corresponding to the labelled sample from the downstream task. We train our model on two HSI datasets, namely Houston dataset (from data fusion contest, 2013) and Pavia university dataset, and show that the proposed approach performs better than self-supervised approach and supervised training.

cs.CV↗

arXiv2023

USIM-DAL: Uncertainty-aware Statistical Image Modeling-based Dense Active Learning for Super-resolution

Dense regression is a widely used approach in computer vision for tasks such as image super-resolution, enhancement, depth estimation, etc. However, the high cost of annotation and labeling makes it challenging to achieve accurate results. We propose incorporating active learning into dense regression models to address this problem. Active learning allows models to select the most informative samples for labeling, reducing the overall annotation cost while improving performance. Despite its potential, active learning has not been widely explored in high-dimensional computer vision regression tasks like super-resolution. We address this research gap and propose a new framework called USIM-DAL that leverages the statistical properties of colour images to learn informative priors using probabilistic deep neural networks that model the heteroscedastic predictive distribution allowing uncertainty quantification. Moreover, the aleatoric uncertainty from the network serves as a proxy for error that is used for active learning. Our experiments on a wide variety of datasets spanning applications in natural images (visual genome, BSD100), medical imaging (histopathology slides), and remote sensing (satellite images) demonstrate the efficacy of the newly proposed USIM-DAL and superiority over several dense regression active learning methods.

cs.CV↗

arXiv2023

APPLeNet: Visual Attention Parameterized Prompt Learning for Few-Shot Remote Sensing Image Generalization using CLIP

In recent years, the success of large-scale vision-language models (VLMs) such as CLIP has led to their increased usage in various computer vision tasks. These models enable zero-shot inference through carefully crafted instructional text prompts without task-specific supervision. However, the potential of VLMs for generalization tasks in remote sensing (RS) has not been fully realized. To address this research gap, we propose a novel image-conditioned prompt learning strategy called the Visual Attention Parameterized Prompts Learning Network (APPLeNet). APPLeNet emphasizes the importance of multi-scale feature learning in RS scene classification and disentangles visual style and content primitives for domain generalization tasks. To achieve this, APPLeNet combines visual content features obtained from different layers of the vision encoder and style properties obtained from feature statistics of domain-specific batches. An attention-driven injection module is further introduced to generate visual tokens from this information. We also introduce an anti-correlation regularizer to ensure discrimination among the token embeddings, as this visual information is combined with the textual tokens. To validate APPLeNet, we curated four available RS benchmarks and introduced experimental protocols and datasets for three domain generalization tasks. Our results consistently outperform the relevant literature and code is available at https://github.com/mainaksingha01/APPLeNet

cs.CV↗

arXiv2023

Prototypical quadruplet for few-shot class incremental learning

Scarcity of data and incremental learning of new tasks pose two major bottlenecks for many modern computer vision algorithms. The phenomenon of catastrophic forgetting, i.e., the model's inability to classify previously learned data after training with new batches of data, is a major challenge. Conventional methods address catastrophic forgetting while compromising the current session's training. Generative replay-based approaches, such as generative adversarial networks (GANs), have been proposed to mitigate catastrophic forgetting, but training GANs with few samples may lead to instability. To address these challenges, we propose a novel method that improves classification robustness by identifying a better embedding space using an improved contrasting loss. Our approach retains previously acquired knowledge in the embedding space, even when trained with new classes, by updating previous session class prototypes to represent the true class mean, which is crucial for our nearest class mean classification strategy. We demonstrate the effectiveness of our method by showing that the embedding space remains intact after training the model with new classes and outperforms existing state-of-the-art algorithms in terms of accuracy across different sessions.

cs.CV↗

arXiv2023

MultiScale Probability Map guided Index Pooling with Attention-based learning for Road and Building Segmentation

Efficient road and building footprint extraction from satellite images are predominant in many remote sensing applications. However, precise segmentation map extraction is quite challenging due to the diverse building structures camouflaged by trees, similar spectral responses between the roads and buildings, and occlusions by heterogeneous traffic over the roads. Existing convolutional neural network (CNN)-based methods focus on either enriched spatial semantics learning for the building extraction or the fine-grained road topology extraction. The profound semantic information loss due to the traditional pooling mechanisms in CNN generates fragmented and disconnected road maps and poorly segmented boundaries for the densely spaced small buildings in complex surroundings. In this paper, we propose a novel attention-aware segmentation framework, Multi-Scale Supervised Dilated Multiple-Path Attention Network (MSSDMPA-Net), equipped with two new modules Dynamic Attention Map Guided Index Pooling (DAMIP) and Dynamic Attention Map Guided Spatial and Channel Attention (DAMSCA) to precisely extract the building footprints and road maps from remotely sensed images. DAMIP mines the salient features by employing a novel index pooling mechanism to retain important geometric information. On the other hand, DAMSCA simultaneously extracts the multi-scale spatial and spectral features. Besides, using dilated convolution and multi-scale deep supervision in optimizing MSSDMPA-Net helps achieve stellar performance. Experimental results over multiple benchmark building and road extraction datasets, ensures MSSDMPA-Net as the state-of-the-art (SOTA) method for building and road extraction.

cs.CV↗

arXiv2022

Zero-Shot Sketch Based Image Retrieval using Graph Transformer

The performance of a zero-shot sketch-based image retrieval (ZS-SBIR) task is primarily affected by two challenges. The substantial domain gap between image and sketch features needs to be bridged, while at the same time the side information has to be chosen tactfully. Existing literature has shown that varying the semantic side information greatly affects the performance of ZS-SBIR. To this end, we propose a novel graph transformer based zero-shot sketch-based image retrieval (GTZSR) framework for solving ZS-SBIR tasks which uses a novel graph transformer to preserve the topology of the classes in the semantic space and propagates the context-graph of the classes within the embedding features of the visual space. To bridge the domain gap between the visual features, we propose minimizing the Wasserstein distance between images and sketches in a learned domain-shared space. We also propose a novel compatibility loss that further aligns the two visual domains by bridging the domain gap of one class with respect to the domain gap of all other classes in the training set. Experimental results obtained on the extended Sketchy, TU-Berlin, and QuickDraw datasets exhibit sharp improvements over the existing state-of-the-art methods in both ZS-SBIR and generalized ZS-SBIR.

cs.CV↗

arXiv2022

RSINet: Inpainting Remotely Sensed Images Using Triple GAN Framework

We tackle the problem of image inpainting in the remote sensing domain. Remote sensing images possess high resolution and geographical variations, that render the conventional inpainting methods less effective. This further entails the requirement of models with high complexity to sufficiently capture the spectral, spatial and textural nuances within an image, emerging from its high spatial variability. To this end, we propose a novel inpainting method that individually focuses on each aspect of an image such as edges, colour and texture using a task specific GAN. Moreover, each individual GAN also incorporates the attention mechanism that explicitly extracts the spectral and spatial features. To ensure consistent gradient flow, the model uses residual learning paradigm, thus simultaneously working with high and low level features. We evaluate our model, alongwith previous state of the art models, on the two well known remote sensing datasets, Open Cities AI and Earth on Canvas, and achieve competitive performance.

cs.CV↗

arXiv2022

BDA-SketRet: Bi-Level Domain Adaptation for Zero-Shot SBIR

The efficacy of zero-shot sketch-based image retrieval (ZS-SBIR) models is governed by two challenges. The immense distributions-gap between the sketches and the images requires a proper domain alignment. Moreover, the fine-grained nature of the task and the high intra-class variance of many categories necessitates a class-wise discriminative mapping among the sketch, image, and the semantic spaces. Under this premise, we propose BDA-SketRet, a novel ZS-SBIR framework performing a bi-level domain adaptation for aligning the spatial and semantic features of the visual data pairs progressively. In order to highlight the shared features and reduce the effects of any sketch or image-specific artifacts, we propose a novel symmetric loss function based on the notion of information bottleneck for aligning the semantic features while a cross-entropy-based adversarial loss is introduced to align the spatial feature maps. Finally, our CNN-based model confirms the discriminativeness of the shared latent space through a novel topology-preserving semantic projection network. Experimental results on the extended Sketchy, TU-Berlin, and QuickDraw datasets exhibit sharp improvements over the literature.

cs.CV↗

arXiv2022

FRIDA -- Generative Feature Replay for Incremental Domain Adaptation

We tackle the novel problem of incremental unsupervised domain adaptation (IDA) in this paper. We assume that a labeled source domain and different unlabeled target domains are incrementally observed with the constraint that data corresponding to the current domain is only available at a time. The goal is to preserve the accuracies for all the past domains while generalizing well for the current domain. The IDA setup suffers due to the abrupt differences among the domains and the unavailability of past data including the source domain. Inspired by the notion of generative feature replay, we propose a novel framework called Feature Replay based Incremental Domain Adaptation (FRIDA) which leverages a new incremental generative adversarial network (GAN) called domain-generic auxiliary classification GAN (DGAC-GAN) for producing domain-specific feature representations seamlessly. For domain alignment, we propose a simple extension of the popular domain adversarial neural network (DANN) called DANN-IB which encourages discriminative domain-invariant and task-relevant feature learning. Experimental results on Office-Home, Office-CalTech, and DomainNet datasets confirm that FRIDA maintains superior stability-plasticity trade-off than the literature.

cs.CV↗

arXiv2022

Teaching CNNs to mimic Human Visual Cognitive Process & regularise Texture-Shape bias

Recent experiments in computer vision demonstrate texture bias as the primary reason for supreme results in models employing Convolutional Neural Networks (CNNs), conflicting with early works claiming that these networks identify objects using shape. It is believed that the cost function forces the CNN to take a greedy approach and develop a proclivity for local information like texture to increase accuracy, thus failing to explore any global statistics. We propose CognitiveCNN, a new intuitive architecture, inspired from feature integration theory in psychology to utilise human interpretable feature like shape, texture, edges etc. to reconstruct, and classify the image. We define novel metrics to quantify the "relevance" of "abstract information" present in these modalities using attention maps. We further introduce a regularisation method which ensures that each modality like shape, texture etc. gets proportionate influence in a given task, as it does for reconstruction; and perform experiments to show the resulting boost in accuracy and robustness, besides imparting explainability to these CNNs for achieving superior performance in object recognition.

cs.CV↗

arXiv2021

A distillation based approach for the diagnosis of diseases

Presently, Covid-19 is a serious threat to the world at large. Efforts are being made to reduce disease screening times and in the development of a vaccine to resist this disease, even as thousands succumb to it everyday. We propose a novel method of automated screening of diseases like Covid-19 and pneumonia from Chest X-Ray images with the help of Computer Vision. Unlike computer vision classification algorithms which come with heavy computational costs, we propose a knowledge distillation based approach which allows us to bring down the model depth, while preserving the accuracy. We make use of an augmentation of the standard distillation module with an auxiliary intermediate assistant network that aids in the continuity of the flow of information. Following this approach, we are able to build an extremely light student network, consisting of just 3 convolutional blocks without any compromise on accuracy. We thus propose a method of classification of diseases which can not only lead to faster screening, but can also operate seamlessly on low-end devices.

cs.CV↗

arXiv2021

Two Headed Dragons: Multimodal Fusion and Cross Modal Transactions

As the field of remote sensing is evolving, we witness the accumulation of information from several modalities, such as multispectral (MS), hyperspectral (HSI), LiDAR etc. Each of these modalities possess its own distinct characteristics and when combined synergistically, perform very well in the recognition and classification tasks. However, fusing multiple modalities in remote sensing is cumbersome due to highly disparate domains. Furthermore, the existing methods do not facilitate cross-modal interactions. To this end, we propose a novel transformer based fusion method for HSI and LiDAR modalities. The model is composed of stacked auto encoders that harness the cross key-value pairs for HSI and LiDAR, thus establishing a communication between the two modalities, while simultaneously using the CNNs to extract the spectral and spatial information from HSI and LiDAR. We test our model on Houston (Data Fusion Contest - 2013) and MUUFL Gulfport datasets and achieve competitive results.

cs.CV↗

arXiv2021

Federated Action Recognition on Heterogeneous Embedded Devices

Federated learning allows a large number of devices to jointly learn a model without sharing data. In this work, we enable clients with limited computing power to perform action recognition, a computationally heavy task. We first perform model compression at the central server through knowledge distillation on a large dataset. This allows the model to learn complex features and serves as an initialization for model fine-tuning. The fine-tuning is required because the limited data present in smaller datasets is not adequate for action recognition models to learn complex spatio-temporal features. Because the clients present are often heterogeneous in their computing resources, we use an asynchronous federated optimization and we further show a convergence bound. We compare our approach to two baseline approaches: fine-tuning at the central server (no clients) and fine-tuning using (heterogeneous) clients using synchronous federated averaging. We empirically show on a testbed of heterogeneous embedded devices that we can perform action recognition with comparable accuracy to the two baselines above, while our asynchronous learning strategy reduces the training time by 40%, relative to synchronous learning.

cs.DC↗

arXiv2021

CrossATNet - A Novel Cross-Attention Based Framework for Sketch-Based Image Retrieval

We propose a novel framework for cross-modal zero-shot learning (ZSL) in the context of sketch-based image retrieval (SBIR). Conventionally, the SBIR schema mainly considers simultaneous mappings among the two image views and the semantic side information. Therefore, it is desirable to consider fine-grained classes mainly in the sketch domain using highly discriminative and semantically rich feature space. However, the existing deep generative modeling-based SBIR approaches majorly focus on bridging the gaps between the seen and unseen classes by generating pseudo-unseen-class samples. Besides, violating the ZSL protocol by not utilizing any unseen-class information during training, such techniques do not pay explicit attention to modeling the discriminative nature of the shared space. Also, we note that learning a unified feature space for both the multi-view visual data is a tedious task considering the significant domain difference between sketches and color images. In this respect, as a remedy, we introduce a novel framework for zero-shot SBIR. While we define a cross-modal triplet loss to ensure the discriminative nature of the shared space, an innovative cross-modal attention learning strategy is also proposed to guide feature extraction from the image domain exploiting information from the respective sketch counterpart. In order to preserve the semantic consistency of the shared space, we consider a graph CNN-based module that propagates the semantic class topology to the shared space. To ensure an improved response time during inference, we further explore the possibility of representing the shared space in terms of hash codes. Experimental results obtained on the benchmark TU-Berlin and the Sketchy datasets confirm the superiority of CrossATNet in yielding state-of-the-art results.

cs.CV↗