Navlika Singh

Abhirama Subramanyam Penamakuri, Navlika Singh, Piyush Arora et al.

Large Vision-Language Models (L-VLMs) have demonstrated remarkable performance in various vision and language tasks, including visual question answering (VQA). However, their high computational cost makes them impractical for resource-constrained settings and inference-heavy applications. In contrast, Small Vision-Language Models (S-VLMs) offer efficiency but suffer from a significant performance gap compared to their larger counterparts. In this work, we introduce the Model Parity Aligner (MPA), a novel framework designed to systematically improve S-VLMs by leveraging unlabeled images and effective knowledge transfer from L-VLMs. Instead of traditional knowledge distillation methods that rely on labeled training data, MPA employs a strategic parity-based approach that precisely identifies the knowledge disparities between S-VLMs and L-VLMs, and optimizes training by targeting only these disparities. We conduct extensive experiments on four diverse VQA benchmarks, namely TextVQA, ST-VQA, ChartQA, and OKVQA, each of which requires specialized reasoning capabilities such as text recognition, chart interpretation, and commonsense and factual understanding. Our results demonstrate that MPA consistently enhances the performance of S-VLMs on all benchmarks, reducing the performance gap while maintaining computational efficiency. We make our code publicly available.

Piyush Arora, Navlika Singh, Vasubhya Diwan et al.

Neural networks have revolutionized numerous fields, yet they remain vulnerable to a critical flaw: the tendency to learn implicit biases, spurious correlations between certain attributes and target labels in training data. These biases are often more prevalent and easier to learn, causing models to rely on superficial patterns rather than task-relevant features necessary for generalization. Existing methods typically rely on strong assumptions, such as prior knowledge of these biases or access to bias-conflicting samples, i.e., samples that contradict spurious correlations and counterbalance bias-aligned samples, samples that conform to these spurious correlations. However, such assumptions are often impractical in real-world settings. We propose BLADE ({B}ias-{L}inked {A}daptive {DE}biasing), a generative debiasing framework that requires no prior knowledge of bias or bias-conflicting samples. BLADE first trains a generative model to translate images across bias domains while preserving task-relevant features. Then, it adaptively refines each image with its synthetic counterpart based on the image's susceptibility to bias. To encourage robust representations, BLADE aligns an image with its bias-translated synthetic counterpart that shares task-relevant features but differs in bias, while misaligning it with samples sharing the same bias. We evaluate BLADE on multiple benchmark datasets and show that it significantly outperforms state-of-the-art methods. Notably, it exceeds the closest baseline by an absolute margin of around 18% on the corrupted CIFAR-10 dataset under the worst group setting, establishing a new benchmark in bias mitigation and demonstrating its potential for developing more robust deep learning models without explicit supervision.