Philip H. S. Torr
11 papers in the PaperMetrix corpus
Papers by this author
-
Learn To Pay Attention
2018 · arXiv (Cornell University)
We propose an end-to-end-trainable attention module for convolutional neural network (CNN) architectures built for image classification. The module takes as input the 2D feature vector maps which form the intermediate representations of the input image …
-
Low Rank Structure of Learned Representations.
2018 · arXiv (Cornell University)
A key feature of neural networks, particularly deep convolutional neural networks, is their ability to learn useful representations from data. The very last layer of a neural network is then simply a linear model trained …
-
Calibrating Deep Neural Networks using Focal Loss
2020 · arXiv (Cornell University)
Miscalibration - a mismatch between a model's confidence and its correctness - of Deep Neural Networks (DNNs) makes their predictions hard to rely on. Ideally, we want networks to be accurate, calibrated and confident. We …
-
Continual Learning in Low-rank Orthogonal Subspaces
2020 · arXiv (Cornell University)
In continual learning (CL), a learner is faced with a sequence of tasks, arriving one after the other, and the goal is to remember all the tasks once the continual learning experience is finished. The …
-
Computationally Budgeted Continual Learning: What Does Matter?
2023 · arXiv (Cornell University)
Continual Learning (CL) aims to sequentially train models on streams of incoming data that vary in distribution by preserving previous knowledge while adapting to new data. Current CL literature focuses on restricted access to previously …
-
Online Continual Learning Without the Storage Constraint
2023 · arXiv (Cornell University)
Traditional online continual learning (OCL) research has primarily focused on mitigating catastrophic forgetting with fixed and limited storage allocation throughout an agent's lifetime. However, a broad range of real-world applications are primarily constrained by computational …
-
Graph Inductive Biases in Transformers without Message Passing
2023 · arXiv (Cornell University)
Transformers for graph data are increasingly widely studied and successful in numerous learning tasks. Graph inductive biases are crucial for Graph Transformers, and previous works incorporate them using message-passing modules and/or positional encodings. However, Graph …
-
Don’t FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs
2023
In this paper we investigate the frequency sensitivity of Deep Neural Networks (DNNs) when presented with clean samples versus poisoned samples. Our analysis shows significant disparities in frequency sensitivity between these two types of samples. …
-
From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web
2023 · arXiv (Cornell University)
Continual Learning (CL) often relies on the availability of extensive annotated datasets, an assumption that is unrealistically time-consuming and costly in practice. We explore a novel paradigm termed name-only continual learning where time and cost …
-
Random Representations Outperform Online Continually Learned Representations
2024 · arXiv (Cornell University)
Continual learning has primarily focused on the issue of catastrophic forgetting and the associated stability-plasticity tradeoffs. However, little attention has been paid to the efficacy of continually learned representations, as representations are learned alongside classifiers …
-
Plain Transformers Can be Powerful Graph Learners
2025 · arXiv (Cornell University)
Transformers have attained outstanding performance across various modalities, owing to their simple but powerful scaled-dot-product (SDP) attention mechanisms. Researchers have attempted to migrate Transformers to graph learning, but most advanced Graph Transformers (GTs) have strayed …