Browse SoTA > Computer Vision > Image Classification

Image Classification

1161 papers with code · Computer Vision

Image Classification is a fundamental task that attempts to comprehend an entire image as a whole. The goal is to classify the image by assigning it to a specific label. Typically, Image Classification refers to images in which only one object appears and is analyzed. In contrast, object detection involves both classification and localization tasks, and is used to analyze more realistic cases in which multiple objects may exist in an image.

Source: Metamorphic Testing for Object Detection Systems

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Latest papers with code

LambdaNetworks: Modeling long-range Interactions without Attention

ICLR 2021 lucidrains/lambda-networks

We present a general framework for capturing long-range interactions between an input and structured contextual information (e. g. a pixel surrounded by other pixels).

IMAGE CLASSIFICATION INSTANCE SEGMENTATION OBJECT DETECTION SCENE SEGMENTATION

994
01 Jan 2021

Improving Random-Sampling Neural Architecture Search by Evolving the Proxy Search Space

ICLR 2021 IcLr2020SuBmIsSiOn/EPS

This raises the question of whether we can find an effective proxy search space (PS) that is only a small subset of GS to dramatically improve RandomNAS’s search efficiency while at the same time keeping a good correlation for the top-performing architectures.

IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH

1
01 Jan 2021

Contrast to Divide: self-supervised pre-training for learning with noisy labels

ICLR 2021 ContrastToDivide/C2D

Advances in semi-supervised methods for image classification significantly boosted performance in the learning with noisy labels (LNL) task.

LEARNING WITH NOISY LABELS

1
01 Jan 2021

Permute, Quantize, and Fine-tune: Efficient Compression of Neural Networks

29 Oct 2020uber-research/permute-quantize-finetune

Compressing large neural networks is an important step for their deployment in resource-constrained computational platforms.

IMAGE CLASSIFICATION OBJECT DETECTION QUANTIZATION

22
29 Oct 2020

Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases

28 Oct 2020ryansteed/ieat

Recent advances in machine learning leverage massive datasets of unlabeled images from the web to learn general-purpose image representations for tasks from image classification to face recognition.

FACE RECOGNITION IMAGE CLASSIFICATION UNSUPERVISED PRE-TRAINING

1
28 Oct 2020

Classification Beats Regression: Counting of Cells from Greyscale Microscopic Images based on Annotation-free Training Samples

28 Oct 2020UBCDingXin/CellCount_TinyBBBC005

Modern methods often formulate the counting of cells from microscopic images as a regression problem and more or less rely on expensive, manually annotated training images (e. g., dot annotations indicating the centroids of cells or segmentation masks identifying the contours of cells).

DATA AUGMENTATION IMAGE CLASSIFICATION

0
28 Oct 2020

μNAS: Constrained Neural Architecture Search for Microcontrollers

27 Oct 2020eliberis/uNAS

IoT devices are powered by microcontroller units (MCUs) which are extremely resource-scarce: a typical MCU may have an underpowered processor and around 64 KB of memory and persistent storage, which is orders of magnitude fewer computational resources than is typically required for deep learning.

IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH

2
27 Oct 2020

Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians

26 Oct 2020pomonam/Self-Tuning-Networks

Hyperparameter optimization of neural networks can be elegantly formulated as a bilevel optimization problem.

BILEVEL OPTIMIZATION HYPERPARAMETER OPTIMIZATION IMAGE CLASSIFICATION

20
26 Oct 2020

Real-Time Edge Classification: Optimal Offloading under Token Bucket Constraints

26 Oct 2020ayanc/edgeml.mdp

To deploy machine learning-based algorithms for real-time applications with strict latency constraints, we consider an edge-computing setting where a subset of inputs are offloaded to the edge for processing by an accurate but resource-intensive model, and the rest are processed only by a less-accurate model on the device itself.

IMAGE CLASSIFICATION

1
26 Oct 2020

Scalable Bayesian neural networks by layer-wise input augmentation

26 Oct 2020trungtrinh44/ibnn

We introduce implicit Bayesian neural networks, a simple and scalable approach for uncertainty representation in deep learning.

IMAGE CLASSIFICATION

0
26 Oct 2020