Vinay Verma

Varun Khare, Divyat Mahajan, Homanga Bharadhwaj et al.

We present a domain adaptation based generative framework for zero-shot learning. Our framework addresses the problem of domain shift between the seen and unseen class distributions in zero-shot learning and minimizes the shift by developing a generative model trained via adversarial domain adaptation. Our approach is based on end-to-end learning of the class distributions of seen classes and unseen classes. To enable the model to learn the class distributions of unseen classes, we parameterize these class distributions in terms of the class attribute information (which is available for both seen and unseen classes). This provides a very simple way to learn the class distribution of any unseen class, given only its class attribute information, and no labeled training data. Training this model with adversarial domain adaptation further provides robustness against the distribution mismatch between the data from seen and unseen classes. Our approach also provides a novel way for training neural net based classifiers to overcome the hubness problem in zero-shot learning. Through a comprehensive set of experiments, we show that our model yields superior accuracies as compared to various state-of-the-art zero shot learning models, on a variety of benchmark datasets. Code for the experiments is available at github.com/vkkhare/ZSL-ADA

Soumya Roy, Soumya Banerjee, Vinay Verma et al.

Machine unlearning (MUL) refers to the problem of making a pre-trained model selectively forget some training instances or class(es) while retaining performance on the remaining dataset. Existing MUL research involves fine-tuning using a forget and/or retain set, making it expensive and/or impractical, and often causing performance degradation in the unlearned model. We introduce {\pname}, an unlearning-aware vision transformer-based architecture that can directly perform unlearning for future unlearning requests without any fine-tuning over the requested set. The proposed model is trained by simulating unlearning during the training process itself. It involves randomly separating class(es)/sub-class(es) present in each mini-batch into two disjoint sets: a proxy forget-set and a retain-set, and the model is optimized so that it is unable to predict the forget-set. Forgetting is achieved by withdrawing keys, making unlearning on-the-fly and avoiding performance degradation. The model is trained jointly with learnable keys and original weights, ensuring withholding a key irreversibly erases information, validated by membership inference attack scores. Extensive experiments on various datasets, architectures, and resolutions confirm {\pname}'s superiority over both fine-tuning-free and fine-tuning-based methods.

Soham Mitra, Atri Sukul, Swalpa Kumar Roy et al.

Deep learning models have achieved remarkable success across diverse domains. However, the intricate nature of these models often impedes a clear understanding of their decision-making processes. This is where Explainable AI (XAI) becomes indispensable, offering intuitive explanations for model decisions. In this work, we propose a simple yet highly effective approach, ScoreCAM++, which introduces modifications to enhance the promising ScoreCAM method for visual explainability. Our proposed approach involves altering the normalization function within the activation layer utilized in ScoreCAM, resulting in significantly improved results compared to previous efforts. Additionally, we apply an activation function to the upsampled activation layers to enhance interpretability. This improvement is achieved by selectively gating lower-priority values within the activation layer. Through extensive experiments and qualitative comparisons, we demonstrate that ScoreCAM++ consistently achieves notably superior performance and fairness in interpreting the decision-making process compared to both ScoreCAM and previous methods.

Vinay Verma, Deepak Singh, Nitin Khanna

The double JPEG compression detection has received much attention in recent years due to its applicability as a forensic tool for the most widely used JPEG file format. Existing state-of-the-art CNN-based methods either use histograms of all the frequencies or rely on heuristics to select histograms of specific low frequencies to classify single and double compressed images. However, even amidst lower frequencies of double compressed images/patches, histograms of all the frequencies do not have distinguishable features to separate them from single compressed images. This paper directly extracts the quantized DCT coefficients from the JPEG images without decompressing them in the pixel domain, obtains all AC frequencies' histograms, uses a module based on $1\times 1$ depth-wise convolutions to learn the inherent relation between each histogram and corresponding q-factor, and utilizes a tailor-made BiLSTM network for selectively encoding these feature vector sequences. The proposed system outperforms several baseline methods on a relatively large and diverse publicly available dataset of single and double compressed patches. Another essential aspect of any single vs. double JPEG compression detection system is handling the scenario where test patches are compressed with entirely different quantization matrices (Q-matrices) than those used while training; different camera manufacturers and image processing software generally utilize their customized quantization matrices. A set of extensive experiments shows that the proposed system trained on a single dataset generalizes well on other datasets compressed with completely unseen quantization matrices and outperforms the state-of-the-art methods in both seen and unseen quantization matrices scenarios.

Vinay Verma, Nikita Agarwal, Nitin Khanna

With the rapid advancements in digital imaging systems and networking, low-cost hand-held image capture devices equipped with network connectivity are becoming ubiquitous. This ease of digital image capture and sharing is also accompanied by widespread usage of user-friendly image editing software. Thus, we are in an era where digital images can be very easily used for the massive spread of false information and their integrity need to be seriously questioned. Application of multiple lossy compressions on images is an essential part of any image editing pipeline involving lossy compressed images. This paper aims to address the problem of classifying images based on the number of JPEG compressions they have undergone, by utilizing deep convolutional neural networks in DCT domain. The proposed system incorporates a well designed pre-processing step before feeding the image data to CNN to capture essential characteristics of compression artifacts and make the system image content independent. Detailed experiments are performed to optimize different aspects of the system, such as depth of CNN, number of DCT frequencies, and execution time. Results on the standard UCID dataset demonstrate that the proposed system outperforms existing systems for multiple JPEG compression detection and is capable of classifying more number of re-compression cycles then existing systems.