Rohan Wadhawan

Rohan Wadhawan, Fabrice Y Harel-Canada, Zi-Yi Dou et al.

Preference finetuning methods like Direct Preference Optimization (DPO) with AI-generated feedback have shown promise in aligning Large Vision-Language Models (LVLMs) with human preferences. However, existing techniques overlook the prevalence of noise in synthetic preference annotations in the form of stylistic and length biases. To this end, we introduce a hard-negative response generation framework based on LLM-guided response editing, that produces rejected responses with targeted errors, maintaining stylistic and length similarity to the accepted ones. Using this framework, we develop the VaPR dataset, comprising 30K high-quality samples, to finetune three LVLM families: LLaVA-V1.5, Qwen2VL & Qwen2.5VL (2B-13B sizes). Our VaPR models deliver significant performance improvements across ten benchmarks, achieving average gains of 6.5% (LLaVA), 4.0% (Qwen2VL), and 1.5% (Qwen2.5VL), with notable improvements on reasoning tasks. A scaling analysis shows that performance consistently improves with data size, with LLaVA models benefiting even at smaller scales. Moreover, VaPR reduces the tendency to answer "Yes" in binary questions - addressing a common failure mode in LVLMs like LLaVA. Lastly, we show that the framework generalizes to open-source LLMs as editors, with models trained on VaPR-OS achieving ~99% of the performance of models trained on \name, which is synthesized using GPT-4o. Our data, models, and code can be found on the project page https://vap-r.github.io

Michael Cooper, Rohan Wadhawan, John Michael Giorgi et al.

Decision-makers often possess insufficient information to render a confident decision. In these cases, the decision-maker can often undertake actions to acquire the necessary information about the problem at hand, e.g., by consulting knowledgeable authorities or by conducting experiments. Importantly, different levers of information acquisition come with different costs, posing the challenge of selecting the actions that are both informative and cost-effective. In this work, we propose CuriosiTree, a heuristic-based, test-time policy for zero-shot information acquisition in large language models (LLMs). CuriosiTree employs a greedy tree search to estimate the expected information gain of each action and strategically chooses actions based on a balance of anticipated information gain and associated cost. Empirical validation in a clinical diagnosis simulation shows that CuriosiTree enables cost-effective integration of heterogenous sources of information, and outperforms baseline action selection strategies in selecting action sequences that enable accurate diagnosis.

Rohan Wadhawan, Hritik Bansal, Kai-Wei Chang et al.

Many real-world tasks require an agent to reason jointly over text and visual objects, (e.g., navigating in public spaces), which we refer to as context-sensitive text-rich visual reasoning. Specifically, these tasks require an understanding of the context in which the text interacts with visual elements within an image. However, there is a lack of existing datasets to benchmark the state-of-the-art multimodal models' capability on context-sensitive text-rich visual reasoning. In this paper, we introduce ConTextual, a novel dataset featuring human-crafted instructions that require context-sensitive reasoning for text-rich images. We conduct experiments to assess the performance of 14 foundation models (GPT-4V, Gemini-Pro-Vision, LLaVA-Next) and establish a human performance baseline. Further, we perform human evaluations of the model responses and observe a significant performance gap of 30.8% between GPT-4V (the current best-performing Large Multimodal Model) and human performance. Our fine-grained analysis reveals that GPT-4V encounters difficulties interpreting time-related data and infographics. However, it demonstrates proficiency in comprehending abstract visual contexts such as memes and quotes. Finally, our qualitative analysis uncovers various factors contributing to poor performance including lack of precise visual perception and hallucinations. Our dataset, code, and leaderboard can be found on the project page https://con-textual.github.io/

Rohan Wadhawan, Tanuj Drall, Shubham Singh et al.

Generative Adversarial Networks (GANs) have revolutionized image synthesis through many applications like face generation, photograph editing, and image super-resolution. Image synthesis using GANs has predominantly been uni-modal, with few approaches that can synthesize images from text or other data modes. Text-to-image synthesis, especially text-to-face synthesis, has promising use cases of robust face-generation from eye witness accounts and augmentation of the reading experience with visual cues. However, only a couple of datasets provide consolidated face data and textual descriptions for text-to-face synthesis. Moreover, these textual annotations are less extensive and descriptive, which reduces the diversity of faces generated from it. This paper empirically proves that increasing the number of facial attributes in each textual description helps GANs generate more diverse and real-looking faces. To prove this, we propose a new methodology that focuses on using structured textual descriptions. We also consolidate a Multi-Attributed and Structured Text-to-face (MAST) dataset consisting of high-quality images with structured textual annotations and make it available to researchers to experiment and build upon. Lastly, we report benchmark Frechet's Inception Distance (FID), Facial Semantic Similarity (FSS), and Facial Semantic Distance (FSD) scores for the MAST dataset.

Rohan Wadhawan, Tapan K. Gandhi

Facial Expression Recognition from static images is a challenging problem in computer vision applications. Convolutional Neural Network (CNN), the state-of-the-art method for various computer vision tasks, has had limited success in predicting expressions from faces having extreme poses, illumination, and occlusion conditions. To mitigate this issue, CNNs are often accompanied by techniques like transfer, multi-task, or ensemble learning that often provide high accuracy at the cost of increased computational complexity. In this work, we propose a Part-based Ensemble Transfer Learning network that models how humans recognize facial expressions by correlating the spatial orientation pattern of the facial features with a specific expression. It consists of 5 sub-networks, and each sub-network performs transfer learning from one of the five subsets of facial landmarks: eyebrows, eyes, nose, mouth, or jaw to expression classification. We show that our proposed ensemble network uses visual patterns emanating from facial muscles' motor movements to predict expressions and demonstrate the usefulness of transfer learning from Facial Landmark Localization to Facial Expression Recognition. We test the proposed network on the CK+, JAFFE, and SFEW datasets, and it outperforms the benchmark for CK+ and JAFFE datasets by 0.51% and 5.34%, respectively. Additionally, the proposed ensemble network consists of only 1.65M model parameters, ensuring computational efficiency during training and real-time deployment. Grad-CAM visualizations of our proposed ensemble highlight the complementary nature of its sub-networks, a key design parameter of an effective ensemble network. Lastly, cross-dataset evaluation results reveal that our proposed ensemble has a high generalization capacity, making it suitable for real-world usage.

Shiva Azimi, Rohan Wadhawan, Tapan K. Gandhi

In the recent decade, high-throughput plant phenotyping techniques, which combine non-invasive image analysis and machine learning, have been successfully applied to identify and quantify plant health and diseases. However, these techniques usually do not consider the progressive nature of plant stress and often require images showing severe signs of stress to ensure high confidence detection, thereby reducing the feasibility for early detection and recovery of plants under stress. To overcome the problem mentioned above, we propose a deep learning pipeline for the temporal analysis of the visual changes induced in the plant due to stress and apply it to the specific water stress identification case in Chickpea plant shoot images. For this, we have considered an image dataset of two chickpea varieties JG-62 and Pusa-372, under three water stress conditions; control, young seedling, and before flowering, captured over five months. We have employed a variant of Convolutional Neural Network - Long Short Term Memory (CNN-LSTM) network to learn spatio-temporal patterns from the chickpea plant dataset and use them for water stress classification. Our model has achieved ceiling level classification performance of 98.52% on JG-62 and 97.78% on Pusa-372 chickpea plant data and has outperformed the best reported time-invariant technique by at least 14% for both JG-62 and Pusa-372 species, to the best of our knowledge. Furthermore, our CNN-LSTM model has demonstrated robustness to noisy input, with a less than 2.5% dip in average model accuracy and a small standard deviation about the mean for both species. Lastly, we have performed an ablation study to analyze the performance of the CNN-LSTM model by decreasing the number of temporal session data used for training.