tezvyn:

🤖AI & ML

Artificial intelligence, machine learning, and data science

1166 bites

More in AI & ML — page 12

Computer Vision2 min read

Contrastive self-supervised learning with SimCLR

WHAT IT TESTS: contrastive learning mechanics. OUTLINE: two augmentations of one image form a positive pair, other images in the batch are negatives; an encoder plus projection head and the NT-Xent loss pull positives together and push negatives apart.

Computer Vision2 min read

Leveraging unlabeled data with limited labels

WHAT IT TESTS: semi-supervised and self-supervised strategy. OUTLINE: pretrain a representation on the million unlabeled images via self-supervision, then fine-tune on the 1,000 labels; or use pseudo-labeling and consistency regularization.

Computer Vision2 min read

Transfer learning from ResNet50 on small data

WHAT IT TESTS: applying transfer learning. OUTLINE: replace the final classification head with one sized to your classes, freeze the pretrained convolutional backbone as a feature extractor, train the new head, then optionally fine-tune top blocks at a low…

Computer Vision2 min read

Formulating a multi-step robot manipulation task

WHAT IT TESTS: end-to-end robot RL formulation. OUTLINE: perception detects and localizes the mug, action space spans navigation and manipulation, and a reward shaped over subgoals (reach, grasp, transport, place) with sparse final success guides learning.

Computer Vision2 min read

NeRF limitations and advances for robotics

WHAT IT TESTS: practical limits of NeRF. OUTLINE: original NeRF is slow to train and render, per-scene, static, and needs many calibrated views; address speed with explicit grids or Gaussian splatting, dynamics with time-conditioned fields, and scale with…

Computer Vision2 min read

Camera intrinsics, extrinsics, and the essential matrix

WHAT IT TESTS: epipolar geometry fundamentals. OUTLINE: intrinsics map camera coords to pixels, extrinsics are camera pose in the world; the essential matrix relates normalized points across two views, encoding relative rotation and translation up to scale…

Computer Vision2 min read

Designing a baseline Visual Question Answering model

WHAT IT TESTS: multimodal baseline design. OUTLINE: encode the image with a CNN, encode the question with an RNN or embedding, fuse the two vectors, and classify over a fixed answer vocabulary.

Computer Vision2 min read

Semantic, instance, and panoptic segmentation

WHAT IT TESTS: distinguishing segmentation paradigms. OUTLINE: semantic labels every pixel by class without separating objects; instance separates individual objects but may skip background; panoptic unifies both, labeling stuff and distinct thing instances.

Computer Vision2 min read

Designing a high-resolution photorealistic face generator

WHAT IT TESTS: system design for high-res faces. OUTLINE: weigh StyleGAN's fast, controllable style-based synthesis against diffusion's diversity and stable training; handle scale via progressive or multi-resolution synthesis; protect diversity to avoid mode…

Computer Vision2 min read

DDPM versus DDIM sampling trade-offs

WHAT IT TESTS: stochastic versus deterministic sampling. OUTLINE: DDPM is a stochastic Markov chain needing many steps; DDIM is a non-Markovian, deterministic sampler that skips steps for far faster inference and reproducible, invertible latents, trading a…

Computer Vision2 min read

Classifier-free guidance in diffusion models

WHAT IT TESTS: how guidance improves conditioning. OUTLINE: train one model jointly on conditional and dropped-condition inputs; at inference extrapolate from unconditional toward conditional prediction via a guidance scale, sharpening prompt adherence…

Computer Vision2 min read

Unpaired image translation with CycleGAN

WHAT IT TESTS: unpaired translation design. OUTLINE: CycleGAN uses two generators and two discriminators with a cycle-consistency loss that forces translating to the other domain and back to reconstruct the input, removing the need for paired data.

Computer Vision2 min read

How text prompts guide Stable Diffusion

WHAT IT TESTS: the text-conditioning pipeline. OUTLINE: a frozen text encoder turns the prompt into token embeddings, which feed the U-Net via cross-attention at each denoising step so the prompt steers generation; classifier-free guidance amplifies the…

Computer Vision89 sec read

Why U-Net skip connections matter for denoising

WHAT IT TESTS: role of skip connections in denoising. OUTLINE: skips carry high-resolution spatial detail from encoder to decoder, preserving fine structure lost in downsampling and easing gradient flow, which lets the model restore detail while removing…

Computer Vision2 min read

Evaluating generative models with FID versus IS

WHAT IT TESTS: rigorous generative evaluation. OUTLINE: FID compares Inception feature distributions of real and fake images via Frechet distance between two Gaussians; it uses real data as reference and detects diversity issues, unlike IS which uses no real…

Computer Vision2 min read

Mode collapse in GAN training

WHAT IT TESTS: understanding GAN diversity failure. OUTLINE: generator produces few outputs ignoring data diversity, caused by chasing whatever fools the current discriminator; mitigate with minibatch discrimination, unrolled GANs, or Wasserstein loss.

Computer Vision2 min read

Diffusion forward and reverse processes

WHAT IT TESTS: the noise-and-denoise framing. OUTLINE: forward process gradually adds Gaussian noise until data is pure noise; reverse process learns to denoise step by step; the network predicts the noise added at each timestep.

Computer Vision87 sec read

GAN architecture: generator and discriminator roles

WHAT IT TESTS: the adversarial minimax setup. OUTLINE: generator maps noise to fake samples, discriminator classifies real versus fake, they train as a two-player game until samples fool the discriminator.

Computer Vision2 min read

Attention in diffusion U-Nets for text conditioning

WHAT IT TESTS: how text conditioning enters the denoiser. OUTLINE: self-attention mixes spatial features at low-res blocks; cross-attention has image queries attend to text-token keys/values; placed inside transformer blocks.

Computer Vision2 min read

Pure ViT vs hybrid CNN-Transformer for medical segmentation

WHAT IT TESTS: matching architecture to data and task constraints. OUTLINE: pure ViT captures global context but is data hungry and weak on local detail; hybrid CNN-Transformer gets local features cheaply plus global attention, ideal for scarce…