Search Results for author:
Found 42 papers, 20 papers with code
Rethinking Positive Pairs in Contrastive Learning
We challenge this assumption by proposing to learn from arbitrary pairs, allowing any pair of samples to be positive within our framework. The primary challenge of the proposed approach lies in applying contrastive learning to disparate pairs which are semantically distant.
AgroGPT: Efficient Agricultural Vision-Language Model with Expert Tuning
In this work, we propose an approach to construct instruction-tuning data that harnesses vision-only data for the agriculture domain.
AgriCLIP: Adapting CLIP for Agriculture and Livestock via Domain-Specialized Cross-Model Alignment
Further, this domain desires fine-grained feature learning due to the subtle nature of the downstream tasks (e. g, nutrient deficiency detection, livestock breed classification).
Probabilistically Aligned View-unaligned Clustering with Adaptive Template Selection
In most existing multi-view modeling scenarios, cross-view correspondence (CVC) between instances of the same target from different views, like paired image-text data, is a crucial prerequisite for effortlessly deriving a consistent representation.
BAPLe: Backdoor Attacks on Medical Foundational Models using Prompt Learning
Inspired by the latest developments in learnable prompts, this work introduces a method to embed a backdoor into the medical foundation model during the prompt learning phase.
C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition
For evaluating the task, we construct a new benchmark, Something-composition (Sth-com), based on the widely used Something-Something V2 dataset.
BOrg: A Brain Organoid-Based Mitosis Dataset for Automatic Analysis of Brain Diseases
Quantifying cellular processes like mitosis in these organoids offers insights into neurodevelopmental disorders, but the manual analysis is time-consuming, and existing datasets lack specific details for brain organoid studies.
Pseudo Labelling for Enhanced Masked Autoencoders
The targets for pseudo labelling and reconstruction needs to be generated by a teacher network.
Investigating Self-Supervised Methods for Label-Efficient Learning
Vision transformers combined with self-supervised learning have enabled the development of models which scale across large datasets for several downstream tasks like classification, segmentation and detection.
Efficient 3D-Aware Facial Image Editing via Attribute-Specific Prompt Learning
The LAE harnesses a pre-trained vision-language model to find text-guided attribute-specific editing direction in the latent space of any pre-trained 3D-aware GAN.
Revisiting RGBT Tracking Benchmarks from the Perspective of Modality Validity: A New Benchmark, Problem, and Method
We propose a new method based on a mixture of experts, namely MoETrack, as a baseline fusion strategy.
Ranked #3 on
Rgb-T Tracking
on GTOT
MAX-AST: COMBINING CONVOLUTION, LOCAL AND GLOBAL SELF-ATTENTIONS FOR AUDIO EVENT CLASSIFICATION
In the domain of audio transformer architectures, prior research has extensively investigated isotropic architectures that capture the global context through full self-attention and hierarchical architectures that progressively transition from local to global context utilising hierarchical structures with convolutions or window-based attention.
Ranked #23 on
Audio Classification
on AudioSet
DailyMAE: Towards Pretraining Masked Autoencoders in One Day
Recently, masked image modeling (MIM), an important self-supervised learning (SSL) method, has drawn attention for its effectiveness in learning data representation from unlabeled data.
DTF-AT: Decoupled Time-Frequency Audio Transformer for Event Classification
Convolutional neural networks (CNNs) and Transformer-based networks have recently enjoyed significant attention for various audio classification and tagging tasks following their wide adoption in the computer vision domain.
Ranked #15 on
Audio Classification
on AudioSet
DiCoM -- Diverse Concept Modeling towards Enhancing Generalizability in Chest X-Ray Studies
In this context, we introduce Diverse Concept Modeling (DiCoM), a novel self-supervised training paradigm that leverages a student teacher framework for learning diverse concepts and hence effective representation of the CXR data.
LT-ViT: A Vision Transformer for multi-label Chest X-ray classification
Vision Transformers (ViTs) are widely adopted in medical imaging tasks, and some existing efforts have been directed towards vision-language training for Chest X-rays (CXRs).
SCD-Net: Spatiotemporal Clues Disentanglement Network for Self-supervised Skeleton-based Action Recognition
Contrastive learning has achieved great success in skeleton-based action recognition.
Masked Momentum Contrastive Learning for Zero-shot Semantic Understanding
Self-supervised pretraining (SSP) has emerged as a popular technique in machine learning, enabling the extraction of meaningful feature representations without labelled data.
Foundational Models Defining a New Era in Vision: A Survey and Outlook
Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world.
Variantional autoencoder with decremental information bottleneck for disentanglement
One major challenge of disentanglement learning with variational autoencoders is the trade-off between disentanglement and reconstruction fidelity.
SPCXR: Self-supervised Pretraining using Chest X-rays Towards a Domain Specific Foundation Model
However, the traditional diagnostic tool design methods based on supervised learning are burdened by the need to provide training data annotation, which should be of good quality for better clinical outcomes.
Ranked #1 on
Semantic Segmentation
on Montgomery County X-ray Set
ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification
Transformers, which were originally developed for natural language processing, have recently generated significant interest in the computer vision and audio communities due to their flexibility in learning long-range relationships.
SB-SSL: Slice-Based Self-Supervised Transformers for Knee Abnormality Classification from MRI
The availability of large scale data with high quality ground truth labels is a challenge when developing supervised machine learning solutions for healthcare domain.
GMML is All you Need
This has motivated the research in self-supervised transformer pretraining, which does not need to decode the semantic information conveyed by labels to link it to the image properties, but rather focuses directly on extracting a concise representation of the image data that reflects the notion of similarity, and is invariant to nuisance factors.
MC-SSL0.0: Towards Multi-Concept Self-Supervised Learning
In this aspect the proposed SSL frame-work MC-SSL0. 0 is a step towards Multi-Concept Self-Supervised Learning (MC-SSL) that goes beyond modelling single dominant label in an image to effectively utilise the information from all the concepts present in it.
Global Interaction Modelling in Vision Transformer via Super Tokens
Hence, most of the learning is independent of the image patches $(N)$ in the higher layers, and the class embedding is learned solely based on the Super tokens $(N/M^2)$ where $M^2$ is the window size.
MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps
First, we theoretically show the transferability of robustness from an adversarially trained teacher model to a student model with the help of mixup augmentation.
Adversarial Robustness for Unsupervised Domain Adaptation
Extensive Unsupervised Domain Adaptation (UDA) studies have shown great success in practice by learning transferable representations across a labeled source domain and an unlabeled target domain with deep models.
SiT: Self-supervised vIsion Transformer
We also observed that SiT is good for few shot learning and also showed that it is learning useful representation by simply training a linear classifier on top of the learned features from SiT.
NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition
One key ingredient of DCNN-based FR is the appropriate design of a loss function that ensures discrimination between various identities.
AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification
Our framework is novel in its ability to implicitly learn aligned semantics between modalities during the feature learning stage.
Ranked #14 on
Text based Person Retrieval
on CUHK-PEDES
Cross-Modal Person Re-Identification
Cross-Modal Person Re-Identification
+3
A Flatter Loss for Bias Mitigation in Cross-dataset Facial Age Estimation
Compared with existing loss functions, the lower gradient of the proposed loss function leads to the convergence of SGD to a better optimum point, and consequently a better generalisation.
Deep Convolutional Neural Network Ensembles using ECOC
Deep neural networks have enhanced the performance of decision making systems in many applications including image understanding, and further gains can be achieved by constructing ensembles.
Towards an Adversarially Robust Normalization Approach
In this paper, we investigate how BatchNorm causes this vulnerability and proposed new normalization that is robust to adversarial attacks.
A Convolutional Baseline for Person Re-Identification Using Vision and Language Descriptions
However, in real-world surveillance scenarios, frequently no visual information will be available about the queried person.
Leveraging Deep Stein's Unbiased Risk Estimator for Unsupervised X-ray Denoising
Among the plethora of techniques devised to curb the prevalence of noise in medical images, deep learning based approaches have shown the most promise.
Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks
We present a new loss function, namely Wing loss, for robust facial landmark localisation with Convolutional Neural Networks (CNNs).
Ranked #1 on
Face Alignment
on 300W
(NME_inter-pupil (%, Common) metric)
Medical Image Analysis using Convolutional Neural Networks: A Review
Deep learning is successfully used as a tool for machine learning, where a neural network is capable of automatically learning features.
3D Morphable Models as Spatial Transformer Networks
In this paper, we show how a 3D Morphable Model (i. e. a statistical model of the 3D shape of a class of objects such as faces) can be used to spatially transform input data as a module (a 3DMM-STN) within a convolutional neural network.
Face Detection, Bounding Box Aggregation and Pose Estimation for Robust Facial Landmark Localisation in the Wild
The framework has four stages: face detection, bounding box aggregation, pose estimation and landmark localisation.
Medical Image Retrieval using Deep Convolutional Neural Network
The learned features and the classification results are used to retrieve medical images.
