arXiv subjects

Hardik Shah

Publications and source records attributed to Hardik Shah.

14 recordsLinked to original sources

arXiv2026

Unified and Efficient Point-Line Local Features

Multi-view computer vision pipelines typically rely on accurate sparse keypoints and robust descriptors. While incorporating line features has shown clear benefits for matching and pose estimation, existing point-line approaches remain inefficient: they detect points and lines separately, use increasingly heavy networks, and depend on CPU-bound heuristics that hinder real-time performance. We introduce a Unified Efficient Points and Lines (UPAL) feature extractor that jointly extracts keypoints, line segments, and feature descriptors within a single lightweight architecture. A shared backbone provides common representations that feed different branches for point and line features. Line segments are recovered through an accelerated post-processing stage, an enhanced and highly efficient variant of the LSD algorithm. UPAL matches or exceeds state-ofthe-art performance in both point and line applications while significantly reducing computational cost, achieving, for instance, a 4x speedup and 10x smaller memory footprint over the ALIKED + DeepLSD pipeline. Code is publicly available at https://github.com/francois141/upal.

cs.CV↗

arXiv2026

WildOS: Open-Vocabulary Object Search in the Wild

Autonomous navigation in complex, unstructured outdoor environments requires robots to operate over long ranges without prior maps and limited depth sensing. In such settings, relying solely on geometric frontiers for exploration is often insufficient. In such settings, the ability to reason semantically about where to go and what is safe to traverse is crucial for robust, efficient exploration. This work presents WildOS, a unified system for long-range, open-vocabulary object search that combines safe geometric exploration with semantic visual reasoning. WildOS builds a sparse navigation graph to maintain spatial memory, while utilizing a foundation-model-based vision module, ExploRFM, to score frontier nodes of the graph. ExploRFM simultaneously predicts traversability, visual frontiers, and object similarity in image space, enabling real-time, onboard semantic navigation tasks. The resulting vision-scored graph enables the robot to explore semantically meaningful directions while ensuring geometric safety. Furthermore, we introduce a particle-filter-based method for coarse localization of the open-vocabulary target query, that estimates candidate goal positions beyond the robot's immediate depth horizon, enabling effective planning toward distant goals. Extensive closed-loop field experiments across diverse off-road and urban terrains demonstrate that WildOS enables robust navigation, significantly outperforming purely geometric and purely vision-based baselines in both efficiency and autonomy. Our results highlight the potential of vision foundation models to drive open-world robotic behaviors that are both semantically informed and geometrically grounded. Project Page: https://leggedrobotics.github.io/wildos/

cs.RO↗

arXiv2025

ForesightNav: Learning Scene Imagination for Efficient Exploration

Understanding how humans leverage prior knowledge to navigate unseen environments while making exploratory decisions is essential for developing autonomous robots with similar abilities. In this work, we propose ForesightNav, a novel exploration strategy inspired by human imagination and reasoning. Our approach equips robotic agents with the capability to predict contextual information, such as occupancy and semantic details, for unexplored regions. These predictions enable the robot to efficiently select meaningful long-term navigation goals, significantly enhancing exploration in unseen environments. We validate our imagination-based approach using the Structured3D dataset, demonstrating accurate occupancy prediction and superior performance in anticipating unseen scene geometry. Our experiments show that the imagination module improves exploration efficiency in unseen environments, achieving a 100% completion rate for PointNav and an SPL of 67% for ObjectNav on the Structured3D Validation split. These contributions demonstrate the power of imagination-driven reasoning for autonomous systems to enhance generalizable and efficient exploration.

cs.RO↗

arXiv2024

Enhancing End-to-End Multi-Task Dialogue Systems: A Study on Intrinsic Motivation Reinforcement Learning Algorithms for Improved Training and Adaptability

End-to-end multi-task dialogue systems are usually designed with separate modules for the dialogue pipeline. Among these, the policy module is essential for deciding what to do in response to user input. This policy is trained by reinforcement learning algorithms by taking advantage of an environment in which an agent receives feedback in the form of a reward signal. The current dialogue systems, however, only provide meagre and simplistic rewards. Investigating intrinsic motivation reinforcement learning algorithms is the goal of this study. Through this, the agent can quickly accelerate training and improve its capacity to judge the quality of its actions by teaching it an internal incentive system. In particular, we adapt techniques for random network distillation and curiosity-driven reinforcement learning to measure the frequency of state visits and encourage exploration by using semantic similarity between utterances. Experimental results on MultiWOZ, a heterogeneous dataset, show that intrinsic motivation-based debate systems outperform policies that depend on extrinsic incentives. By adopting random network distillation, for example, which is trained using semantic similarity between user-system dialogues, an astounding average success rate of 73% is achieved. This is a significant improvement over the baseline Proximal Policy Optimization (PPO), which has an average success rate of 60%. In addition, performance indicators such as booking rates and completion rates show a 10% rise over the baseline. Furthermore, these intrinsic incentive models help improve the system's policy's resilience in an increasing amount of domains. This implies that they could be useful in scaling up to settings that cover a wider range of domains.

cs.CL↗

arXiv2023

Advancing Web Accessibility -- A guide to transitioning Design Systems from WCAG 2.0 to WCAG 2.1

This research focuses on the critical process of upgrading a Design System from Web Content Accessibility Guidelines (WCAG) 2.0 to WCAG 2.1, which is an essential step in enhancing web accessibility. It emphasizes the importance of staying up to date on increasing accessibility requirements, as well as the critical function of Design Systems in supporting inclusion in digital environments. The article lays out a complete strategy for meeting WCAG 2.1 compliance. Assessment, strategic planning, implementation, and testing are all part of this strategy. The need for collaboration and user involvement is emphasized as critical strategies and best practices for a successful migration journey. In addition, the article digs into migration barriers and discusses significant lessons acquired, offering a realistic view of the intricacies of this transforming road. Finally, it is a practical guide and a necessary resource for organizations committed to accessible and user-centered design. The document provides them with the knowledge and resources they need to navigate the changing world of web accessibility properly.

cs.HC↗

arXiv2023

Harnessing customized built-in elements -- Empowering Component-Based Software Engineering and Design Systems with HTML5 Web Components

Customized built-in elements in HTML5 significantly transform web development. These elements enable developers to create unique HTML components tailored with specific design and purpose. Customized built-in elements enable developers to address the unique needs of web applications more quickly, supporting consistent user interfaces and experiences across diverse digital platforms. This study investigates the role of these features in Component-Based Software Engineering (CBSE) and Design Systems, emphasizing the benefits of code modularity, reusability, and scalability in web development. Customized built-in elements enable developers to address the unique needs of web applications more quickly, supporting consistent user interfaces and experiences across diverse digital platforms. The paper also discusses the difficulties and concerns that must be addressed when creating customized built-in elements, such as browser compatibility, performance optimization, accessibility, security, styling, and interoperability. It emphasizes the importance of standardization, developer tooling, and community interaction in order to fully realize the potential of these features. Looking ahead, customized built-in elements have potential in a variety of applications, including the Internet of Things (IoT), e-commerce, and educational technologies. Their incorporation into Progressive Web Apps (PWAs) is expected to further improve web experiences. While obstacles remain, the article concludes that HTML5 customized built-in elements are a driver for web development innovation, allowing the production of efficient, adaptive, and user-centric web applications in an ever-changing digital context.

cs.SE↗

arXiv2023

Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression

We introduce Style Tailoring, a recipe to finetune Latent Diffusion Models (LDMs) in a distinct domain with high visual quality, prompt alignment and scene diversity. We choose sticker image generation as the target domain, as the images significantly differ from photorealistic samples typically generated by large-scale LDMs. We start with a competent text-to-image model, like Emu, and show that relying on prompt engineering with a photorealistic model to generate stickers leads to poor prompt alignment and scene diversity. To overcome these drawbacks, we first finetune Emu on millions of sticker-like images collected using weak supervision to elicit diversity. Next, we curate human-in-the-loop (HITL) Alignment and Style datasets from model generations, and finetune to improve prompt alignment and style alignment respectively. Sequential finetuning on these datasets poses a tradeoff between better style alignment and prompt alignment gains. To address this tradeoff, we propose a novel fine-tuning method called Style Tailoring, which jointly fits the content and style distribution and achieves best tradeoff. Evaluation results show our method improves visual quality by 14%, prompt alignment by 16.2% and scene diversity by 15.3%, compared to prompt engineering the base Emu model for stickers generation.

cs.CV↗

arXiv2023

VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment

Vision-language pre-training (VLP) has recently proven highly effective for various uni- and multi-modal downstream applications. However, most existing end-to-end VLP methods use high-resolution image-text box data to perform well on fine-grained region-level tasks, such as object detection, segmentation, and referring expression comprehension. Unfortunately, such high-resolution images with accurate bounding box annotations are expensive to collect and use for supervision at scale. In this work, we propose VoLTA (Vision-Language Transformer with weakly-supervised local-feature Alignment), a new VLP paradigm that only utilizes image-caption data but achieves fine-grained region-level image understanding, eliminating the use of expensive box annotations. VoLTA adopts graph optimal transport-based weakly-supervised alignment on local image patches and text tokens to germinate an explicit, self-normalized, and interpretable low-level matching criterion. In addition, VoLTA pushes multi-modal fusion deep into the uni-modal backbones during pre-training and removes fusion-specific transformer layers, further reducing memory requirements. Extensive experiments on a wide range of vision- and vision-language downstream tasks demonstrate the effectiveness of VoLTA on fine-grained applications without compromising the coarse-grained downstream performance, often outperforming methods using significantly more caption and box annotations.

cs.CV↗

arXiv2023

EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone

Video-language pre-training (VLP) has become increasingly important due to its ability to generalize to various vision and language tasks. However, existing egocentric VLP frameworks utilize separate video and language encoders and learn task-specific cross-modal information only during fine-tuning, limiting the development of a unified system. In this work, we introduce the second generation of egocentric video-language pre-training (EgoVLPv2), a significant improvement from the previous generation, by incorporating cross-modal fusion directly into the video and language backbones. EgoVLPv2 learns strong video-text representation during pre-training and reuses the cross-modal attention modules to support different downstream tasks in a flexible and efficient manner, reducing fine-tuning costs. Moreover, our proposed fusion in the backbone strategy is more lightweight and compute-efficient than stacking additional fusion-specific layers. Extensive experiments on a wide range of VL tasks demonstrate the effectiveness of EgoVLPv2 by achieving consistent state-of-the-art performance over strong baselines across all downstream. Our project page can be found at https://shramanpramanick.github.io/EgoVLPv2/.

cs.CV↗

arXiv2023

DIME-FM: DIstilling Multimodal and Efficient Foundation Models

Large Vision-Language Foundation Models (VLFM), such as CLIP, ALIGN and Florence, are trained on large-scale datasets of image-caption pairs and achieve superior transferability and robustness on downstream tasks, but they are difficult to use in many practical applications due to their large size, high latency and fixed architectures. Unfortunately, recent work shows training a small custom VLFM for resource-limited applications is currently very difficult using public and smaller-scale data. In this paper, we introduce a new distillation mechanism (DIME-FM) that allows us to transfer the knowledge contained in large VLFMs to smaller, customized foundation models using a relatively small amount of inexpensive, unpaired images and sentences. We transfer the knowledge from the pre-trained CLIP-ViTL/14 model to a ViT-B/32 model, with only 40M public images and 28.4M unpaired public sentences. The resulting model "Distill-ViT-B/32" rivals the CLIP-ViT-B/32 model pre-trained on its private WiT dataset (400M image-text pairs): Distill-ViT-B/32 achieves similar results in terms of zero-shot and linear-probing performance on both ImageNet and the ELEVATER (20 image classification tasks) benchmarks. It also displays comparable robustness when evaluated on five datasets with natural distribution shifts from ImageNet.

cs.CV↗

arXiv2023

End-to-End Neural Network Compression via $\frac{\ell_1}{\ell_2}$ Regularized Latency Surrogates

Neural network (NN) compression via techniques such as pruning, quantization requires setting compression hyperparameters (e.g., number of channels to be pruned, bitwidths for quantization) for each layer either manually or via neural architecture search (NAS) which can be computationally expensive. We address this problem by providing an end-to-end technique that optimizes for model's Floating Point Operations (FLOPs) or for on-device latency via a novel $\frac{\ell_1}{\ell_2}$ latency surrogate. Our algorithm is versatile and can be used with many popular compression methods including pruning, low-rank factorization, and quantization. Crucially, it is fast and runs in almost the same amount of time as single model training; which is a significant training speed-up over standard NAS methods. For BERT compression on GLUE fine-tuning tasks, we achieve $50\%$ reduction in FLOPs with only $1\%$ drop in performance. For compressing MobileNetV3 on ImageNet-1K, we achieve $15\%$ reduction in FLOPs, and $11\%$ reduction in on-device latency without drop in accuracy, while still requiring $3\times$ less training compute than SOTA compression techniques. Finally, for transfer learning on smaller datasets, our technique identifies $1.2\times$-$1.4\times$ cheaper architectures than standard MobileNetV3, EfficientNet suite of architectures at almost the same training cost and accuracy.

cs.LG↗

arXiv2023

Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks

Searching troves of videos with textual descriptions is a core multimodal retrieval task. Owing to the lack of a purpose-built dataset for text-to-video retrieval, video captioning datasets have been re-purposed to evaluate models by (1) treating captions as positive matches to their respective videos and (2) assuming all other videos to be negatives. However, this methodology leads to a fundamental flaw during evaluation: since captions are marked as relevant only to their original video, many alternate videos also match the caption, which introduces false-negative caption-video pairs. We show that when these false negatives are corrected, a recent state-of-the-art model gains 25\% recall points -- a difference that threatens the validity of the benchmark itself. To diagnose and mitigate this issue, we annotate and release 683K additional caption-video pairs. Using these, we recompute effectiveness scores for three models on two standard benchmarks (MSR-VTT and MSVD). We find that (1) the recomputed metrics are up to 25\% recall points higher for the best models, (2) these benchmarks are nearing saturation for Recall@10, (3) caption length (generality) is related to the number of positives, and (4) annotation costs can be mitigated through sampling. We recommend retiring these benchmarks in their current form, and we make recommendations for future text-to-video retrieval benchmarks.

cs.CL↗

arXiv2022

Tell Your Story: Task-Oriented Dialogs for Interactive Content Creation

People capture photos and videos to relive and share memories of personal significance. Recently, media montages (stories) have become a popular mode of sharing these memories due to their intuitive and powerful storytelling capabilities. However, creating such montages usually involves a lot of manual searches, clicks, and selections that are time-consuming and cumbersome, adversely affecting user experiences. To alleviate this, we propose task-oriented dialogs for montage creation as a novel interactive tool to seamlessly search, compile, and edit montages from a media collection. To the best of our knowledge, our work is the first to leverage multi-turn conversations for such a challenging application, extending the previous literature studying simple media retrieval tasks. We collect a new dataset C3 (Conversational Content Creation), comprising 10k dialogs conditioned on media montages simulated from a large media collection. We take a simulate-and-paraphrase approach to collect these dialogs to be both cost and time efficient, while drawing from natural language distribution. Our analysis and benchmarking of state-of-the-art language models showcase the multimodal challenges present in the dataset. Lastly, we present a real-world mobile demo application that shows the feasibility of the proposed work in real-world applications. Our code and data will be made publicly available.

cs.CL↗

arXiv2012

Dynamic Priority Queue: An SDRAM Arbiter With Bounded Access Latencies for Tight WCET Calculation

This report introduces a shared resource arbitration scheme "DPQ - Dynamic Priority Queue" which provides bandwidth guarantees and low worst case latency to each master in an MPSoC. Being a non-trivial candidate for timing analysis, SDRAM has been chosen as a showcase, but the approach is valid for any shared resource arbitration. Due to its significant cost, data rate and physical size advantages, SDRAM is a potential candidate for cost sensitive, safety critical and space conserving systems. The variable access latency is a major drawback of SDRAM that induces largely over estimated Worst Case Execution Time (WCET) bounds of applications. In this report we present the DPQ together with an algorithm to predict the shared SDRAM's worst case latencies. We use the approach to calculate WCET bounds of six hardware tasks executing on an Altera Cyclone III FPGA with shared DDR2 memory. The results show that the DPQ is a fair arbitration scheme and produces low WCET bounds.

cs.AR↗