Author name cluster

Spandan Madan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

TMLR Journal 2025 Journal Article

Emergent Neural Network Mechanisms for Generalization to Objects in Novel Orientations

Avi Cooper
Daniel Harari
Tomotake Sasaki
Spandan Madan
Hanspeter Pfister
Pawan Sinha
Xavier Boix

The capability of Deep Neural Networks (DNNs) to recognize objects in orientations outside the training data distribution is not well understood. We investigate the limitations of DNNs’ generalization capacities by systematically inspecting DNNs' patterns of success and failure across out-of-distribution (OoD) orientations. We present evidence that DNNs (across architecture types, including convolutional neural networks and transformers) are capable of generalizing to objects in novel orientations, and we describe their generalization behaviors. Specifically, generalization strengthens when training the DNN with an increasing number of familiar objects, but only in orientations that involve 2D rotations of familiar orientations. We also hypothesize how this generalization behavior emerges from internal neural mechanisms – that neurons tuned to common features between familiar and unfamiliar objects enable out of distribution generalization – and present supporting data for this theory. The reproducibility of our findings across model architectures, as well as analogous prior studies on the brain, suggests that these orientation generalization behaviors, as well as the neural mechanisms that drive them, may be a feature of neural networks in general.

PDF Details

TMLR Journal 2025 Journal Article

In-distribution adversarial attacks on object recognition models using gradient-free search.

Spandan Madan
Tomotake Sasaki
Hanspeter Pfister
Tzu-Mao Li
Xavier Boix

Neural networks are susceptible to small perturbations in the form of 2D rotations and shifts, image crops, and even changes in object colors. Past works attribute these errors to dataset bias, claiming that models fail on these perturbed samples as they do not belong to the training data distribution. Here, we challenge this claim and present evidence of the widespread existence of perturbed images within the training data distribution, which networks fail to classify. We train models on data sampled from parametric distributions, then search inside this data distribution to find such in-distribution adversarial examples. This is done using our gradient-free evolution strategies (ES) based approach which we call CMA-Search. Despite training with a large-scale (0.5 million images), unbiased dataset of camera and light variations, CMA-Search can find a failure inside the data distribution in over 71% cases by perturbing the camera position. With lighting changes, CMA-Search finds misclassifications in 42% cases. These findings also extend to natural images from ImageNet and Co3D datasets. This phenomenon of in-distribution images presents a highly worrisome problem for artificial intelligence---they bypass the need for a malicious agent to add engineered noise to induce an adversarial attack. All code, datasets, and demos are available at https://github.com/Spandan-Madan/in_distribution_adversarial_examples.

PDF Details

AAAI Conference 2025 Conference Paper

The Indoor-Training Effect: Unexpected Gains from Distribution Shifts in the Transition Function

Serena Bono
Spandan Madan
Ishaan Grover
Mao Yasueda
Cynthia Breazeal
Hanspeter Pfister
Gabriel Kreiman

Is it better to perform tennis training in a pristine indoor environment or a noisy outdoor one? To model this problem, here we investigate whether shifts in the transition probabilities between the training and testing environments in reinforcement learning problems can lead to better performance under certain conditions. We generate new Markov Decision Processes (MDPs) starting from a given MDP, by adding quantifiable, parametric noise into the transition function. We refer to this process as Noise Injection and the resulting environments as δ-environments. This process allows us to create variations of the same environment with quantitative control over noise serving as a metric of distance between environments. Conventional wisdom suggests that training and testing on the same MDP should yield the best results. In stark contrast, we observe that agents can perform better when trained on the noise-free environment and tested on the noisy δ-environments, compared to training and testing on the same δ-environments. We confirm that this finding extends beyond noise variations: it is possible to showcase the same phenomenon in ATARI game variations including varying Ghost behavior in PacMan, and Paddle behavior in Pong. We demonstrate this intriguing behavior in 60 different variations of ATARI games, including PacMan, Pong, and Breakout. We refer to this phenomenon as the Indoor-Training Effect. Code to reproduce our experiments and to implement Noise Injection.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex.

Spandan Madan
Will Xiao
Mingran Cao
Hanspeter Pfister
Margaret Livingstone
Gabriel Kreiman

We characterized the generalization capabilities of deep neural network encoding models when predicting neuronal responses from the visual cortex to flashed images. We collected MacaqueITBench, a large-scale dataset of neuronal population responses from the macaque inferior temporal (IT) cortex to over $300, 000$ images, comprising $8, 233$ unique natural images presented to seven monkeys over $109$ sessions. Using MacaqueITBench, we investigated the impact of distribution shifts on models predicting neuronal activity by dividing the images into Out-Of-Distribution (OOD) train and test splits. The OOD splits included variations in image contrast, hue, intensity, temperature, and saturation. Compared to the performance on in-distribution test images---the conventional way in which these models have been evaluated---models performed worse at predicting neuronal responses to out-of-distribution images, retaining as little as $20\\%$ of the performance on in-distribution test images. Additionally, the relative ranking of different models in terms of their ability to predict neuronal responses changed drastically across OOD shifts. The generalization performance under OOD shifts can be well accounted by a simple image similarity metric---the cosine distance between image representations extracted from a pre-trained object recognition model is a strong predictor of neuronal predictivity under different distribution shifts. The dataset of images, neuronal firing rate recordings, and computational benchmarks are hosted publicly at: https: //github. com/Spandan-Madan/benchmarking_ood_generalization_visual_cortex.

PDF Details DOI